© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13157
    Prev
    Next
    INDEX
    Explanations

    solid phase, wedding, pharma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     performance
    -0.27
    .performance
    -0.24
    _performance
    -0.22
    -performance
    -0.22
     ÑĢÑĭнке
    -0.21
    åį¸
    -0.20
     product
    -0.20
     market
    -0.20
    aptic
    -0.20
    performance
    -0.20
    POSITIVE LOGITS
    æŁ¥æī¾
    0.30
    åİĨåı²
    0.29
    county
    0.25
    åIJİ代
    0.25
    亲å±ŀ
    0.24
    äºĮ代
    0.24
    æī¾åĪ°
    0.24
    è®°è½½
    0.24
    è®°å½ķ
    0.23
    æ°ijä¿Ĺ
    0.23
    Activations Density 0.042%

    No Known Activations